© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 124545
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pta
    -0.07
    lotte
    -0.07
    alama
    -0.07
    859
    -0.07
    ipi
    -0.07
    arris
    -0.07
    âĻª
    -0.07
    adb
    -0.07
    hiba
    -0.06
    ibo
    -0.06
    POSITIVE LOGITS
     banned
    0.06
    chs
    0.06
     forbidden
    0.06
     prohib
    0.06
     pros
    0.06
     solicit
    0.06
     prohibited
    0.06
     restricted
    0.06
     regul
    0.06
     maj
    0.05
    Activations Density 0.008%

    No Known Activations